GPT-5.4 Pro vs GPT-5.6 Terra

Change models
IndexAll categories, out of 100.
73.3 ±8.7 best
68.9 ±2.0
GapIndex points below the top.
Top
−4.4 · no clear gap
CoverageIndex weight that has results.
60%
100% best
SpeedOutput tokens per second.
21/s
66/s best
EloLMArena rating and rank.
—
1449
ReleasedMonth of release.
2026-03
2026-07
Input / 1MUS dollars per 1M input tokens.
$30.00
$2.00 best
Output / 1MUS dollars per 1M output tokens.
$180.00
$12.00 best
Batch output / 1MBatch price per 1M output tokens.
$90.00
$6.00 best
1K chats2K tokens in, 500 out, each.
$150.00
$10.00 best
1K documents20K tokens in, 1K out, each.
$780.00
$52.00 best
1K agent tasks200K tokens in, 20K out, each.
$9,600.00
$640.00 best
ContextMaximum tokens in one request.
1.05M
1.05M
AgenticMulti-step tasks with tools.
70.5 best
68.2
CodingCode writing and repair.
—
68.4
ReasoningLogic problems and puzzles.
80.4 best
72.5
MultimodalTasks with images and text.
—
67.3
KnowledgeFacts and expert knowledge.
67.2 best
65.5
MultilingualTasks in many languages.
—
60.7
InstructionTasks with strict prompt rules.
—
56.4
MathMath problems.
75.3 best
72.8

Benchmarks

11 shared
Only GPT-5.4 Pro: 7Only GPT-5.6 Terra: 98
GPT-5.4 Pro
GPT-5.6 Terra
94.6% best8 / 217
93.3%19 / 217
30.0%10 / 214
30.0%10 / 214
83.3%19 / 131
83.9% best17 / 131
94.5%21 / 126
96.5% best11 / 126
92.2% best12 / 122
91.3%13 / 122
98.3%8 / 116
98.3%8 / 116
46.3% best40 / 91
43.2%46 / 91
Chess PuzzlesReasoning
59.0% best10 / 90
47.0%24 / 90
82.5%17 / 90
86.0% best13 / 90
58.5%20 / 72
70.7% best17 / 72
BrowseCompAgentic
89.3% best11 / 63
87.5%14 / 63